Languages
Selected completed projects
Contact person: Anton S. Konushin (ktosh@graphics.cs.msu.ru)
Text detection and recognition in natural images
2010-2013
(1) Automatic detection and understanding the text in natural images, such as photographs of city outdoors or building indoors, is a challenging problem. There is a considerable gap between detecting and understanding text in scanned documents (which is a mature technology) and detecting and understanding text in the natural images. Detection and understanding the text in natural photographs involves localizing the text as well as removing the variation factors, such as varying text orientation, font, color and lighting.
Geometric image parsing in man-made environments
2010-2011
We present a new optimization parsing framework for the geometric analysis of a single image coming from a man-made environment. This framework models the scene as a composition of geometric primitives spanning different layers from low level (edges) through mid-level (lines segments, lines and vanishing points) to high level (the zenith and the horizon).
Detection of multiple object instances using Hough transform
2010-2010
In the paper, we develop a new probabilistic framework that is in many ways related to Hough transform, sharing its simplicity and wide applicability. At the same time, the framework bypasses the problem of multiple peaks identification in Hough images, and permits detection of multiple objects without invoking nonmaximum suppression heuristics.
Road monitoring
2008-2009
Roadway video passport systems are widely-used for detailed road mapping which allows roadway quality monitoring and repair planning. The system includes a body of video cameras and other sensors mounted on a car as shown below. The car travels along a road and gathers data from the sensors.
Fast automatic single-view 3-d reconstruction of urban scenes
2007-2008
We consider the problem of estimating 3-d structure from a single still image of an outdoor urban scene. Our goal is to efficiently create 3-d models which are visually pleasant. We chose an appropriate 3-d model structure and formulate the task of 3-d reconstruction as model ?tting problem. Our 3-d models are composed of a number of vertical walls and a ground plane, where ground-vertical boundary is a continuous polyline. We achieve computational efficiency by special preprocessing together with stepwise search of 3-d model parameters dividing the problem into two smaller sub-problems on chain graphs.
Image-based 3D reconstruction of urban scenes
2003-2008
This project is devoted to reconstruction of photo-realistic 3D model of an urban scene from a number of images of streets and crossroads. Our main intention was the createion of a system for construction high-quality models with very simple and intuitive user interface.
Projects
Text detection and recognition in natural images2010-2013
(1) Automatic detection and understanding the text in natural images, such as photographs of city outdoors or building indoors, is a challenging problem. There is a considerable gap between detecting and understanding text in scanned documents (which is a mature technology) and detecting and understanding text in the natural images. Detection and understanding the text in natural photographs involves localizing the text as well as removing the variation factors, such as varying text orientation, font, color and lighting.
Geometric image parsing in man-made environments2010-2011
We present a new optimization parsing framework for the geometric analysis of a single image coming from a man-made environment. This framework models the scene as a composition of geometric primitives spanning different layers from low level (edges) through mid-level (lines segments, lines and vanishing points) to high level (the zenith and the horizon).
Detection of multiple object instances using Hough transform2010-2010
In the paper, we develop a new probabilistic framework that is in many ways related to Hough transform, sharing its simplicity and wide applicability. At the same time, the framework bypasses the problem of multiple peaks identification in Hough images, and permits detection of multiple objects without invoking nonmaximum suppression heuristics.
Road monitoring2008-2009
Roadway video passport systems are widely-used for detailed road mapping which allows roadway quality monitoring and repair planning. The system includes a body of video cameras and other sensors mounted on a car as shown below. The car travels along a road and gathers data from the sensors.
Fast automatic single-view 3-d reconstruction of urban scenes2007-2008
We consider the problem of estimating 3-d structure from a single still image of an outdoor urban scene. Our goal is to efficiently create 3-d models which are visually pleasant. We chose an appropriate 3-d model structure and formulate the task of 3-d reconstruction as model ?tting problem. Our 3-d models are composed of a number of vertical walls and a ground plane, where ground-vertical boundary is a continuous polyline. We achieve computational efficiency by special preprocessing together with stepwise search of 3-d model parameters dividing the problem into two smaller sub-problems on chain graphs.
Image-based 3D reconstruction of urban scenes2003-2008
This project is devoted to reconstruction of photo-realistic 3D model of an urban scene from a number of images of streets and crossroads. Our main intention was the createion of a system for construction high-quality models with very simple and intuitive user interface.
